Identifying translation biases of cognate terms in Chinese textbooks: A GloVe-based method with semantic similarity analysis

With the increasing internationalization of China and the expansion of Chinese language teaching programs, the issue of translation bias in Chinese language textbooks has become increasingly prominent. To improve the accuracy of identifying translation biases in cognate terms, this study proposes a...

Full description

Saved in:
Bibliographic Details
Main Author: Youjing Wang
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Systems and Soft Computing
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772941925001188
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850137336295194624
author Youjing Wang
author_facet Youjing Wang
author_sort Youjing Wang
collection DOAJ
description With the increasing internationalization of China and the expansion of Chinese language teaching programs, the issue of translation bias in Chinese language textbooks has become increasingly prominent. To improve the accuracy of identifying translation biases in cognate terms, this study proposes a diagnostic method based on Global Vectors for Word Representation (GloVe) word embeddings and semantic similarity. The experimental results indicate that the proposed method achieves a maximum diagnostic accuracy of 0.93, with the best diagnostic accuracy for pronouns reaching 0.95, an improvement of 0.8 compared to traditional methods. Additionally, the proposed method maintains an F1 score ranging from 0.85 to 0.94 across multiple datasets, with the lowest false positive rate. This method effectively improves the translation quality of cognate terms in Chinese language textbooks, enhances the scientific accuracy of semantic expression evaluation, and provides strong support for improving textbook proofreading efficiency and the quality of Chinese language teaching.
format Article
id doaj-art-a19ecfd2d54f4ba8bdaef72f042f9344
institution OA Journals
issn 2772-9419
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Systems and Soft Computing
spelling doaj-art-a19ecfd2d54f4ba8bdaef72f042f93442025-08-20T02:30:54ZengElsevierSystems and Soft Computing2772-94192025-12-01720030010.1016/j.sasc.2025.200300Identifying translation biases of cognate terms in Chinese textbooks: A GloVe-based method with semantic similarity analysisYoujing Wang0College of Humanities, Weinan Normal University, Weinan, 714099, ChinaWith the increasing internationalization of China and the expansion of Chinese language teaching programs, the issue of translation bias in Chinese language textbooks has become increasingly prominent. To improve the accuracy of identifying translation biases in cognate terms, this study proposes a diagnostic method based on Global Vectors for Word Representation (GloVe) word embeddings and semantic similarity. The experimental results indicate that the proposed method achieves a maximum diagnostic accuracy of 0.93, with the best diagnostic accuracy for pronouns reaching 0.95, an improvement of 0.8 compared to traditional methods. Additionally, the proposed method maintains an F1 score ranging from 0.85 to 0.94 across multiple datasets, with the lowest false positive rate. This method effectively improves the translation quality of cognate terms in Chinese language textbooks, enhances the scientific accuracy of semantic expression evaluation, and provides strong support for improving textbook proofreading efficiency and the quality of Chinese language teaching.http://www.sciencedirect.com/science/article/pii/S2772941925001188Translation of wordsBiasBinary statisticsGloVe modelChinese as a foreign languageTextbooks
spellingShingle Youjing Wang
Identifying translation biases of cognate terms in Chinese textbooks: A GloVe-based method with semantic similarity analysis
Systems and Soft Computing
Translation of words
Bias
Binary statistics
GloVe model
Chinese as a foreign language
Textbooks
title Identifying translation biases of cognate terms in Chinese textbooks: A GloVe-based method with semantic similarity analysis
title_full Identifying translation biases of cognate terms in Chinese textbooks: A GloVe-based method with semantic similarity analysis
title_fullStr Identifying translation biases of cognate terms in Chinese textbooks: A GloVe-based method with semantic similarity analysis
title_full_unstemmed Identifying translation biases of cognate terms in Chinese textbooks: A GloVe-based method with semantic similarity analysis
title_short Identifying translation biases of cognate terms in Chinese textbooks: A GloVe-based method with semantic similarity analysis
title_sort identifying translation biases of cognate terms in chinese textbooks a glove based method with semantic similarity analysis
topic Translation of words
Bias
Binary statistics
GloVe model
Chinese as a foreign language
Textbooks
url http://www.sciencedirect.com/science/article/pii/S2772941925001188
work_keys_str_mv AT youjingwang identifyingtranslationbiasesofcognatetermsinchinesetextbooksaglovebasedmethodwithsemanticsimilarityanalysis